DGRC: An Effective Fine-tuning Framework for Distractor Generation in Chinese Multi-choice Reading Comprehension

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Runfeng, Xu, Dacheng, Wang, Huijiang, Chen, Zebiao, Wang, Yating, Liu, Shouqiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917678366588928
author Lin, Runfeng
Xu, Dacheng
Wang, Huijiang
Chen, Zebiao
Wang, Yating
Liu, Shouqiang
author_facet Lin, Runfeng
Xu, Dacheng
Wang, Huijiang
Chen, Zebiao
Wang, Yating
Liu, Shouqiang
contents When evaluating a learner's knowledge proficiency, the multiple-choice question is an efficient and widely used format in standardized tests. Nevertheless, generating these questions, particularly plausible distractors (incorrect options), poses a considerable challenge. Generally, the distractor generation can be classified into cloze-style distractor generation (CDG) and natural questions distractor generation (NQDG). In contrast to the CDG, utilizing pre-trained language models (PLMs) for NQDG presents three primary challenges: (1) PLMs are typically trained to generate ``correct'' content, like answers, while rarely trained to generate ``plausible" content, like distractors; (2) PLMs often struggle to produce content that aligns well with specific knowledge and the style of exams; (3) NQDG necessitates the model to produce longer, context-sensitive, and question-relevant distractors. In this study, we introduce a fine-tuning framework named DGRC for NQDG in Chinese multi-choice reading comprehension from authentic examinations. DGRC comprises three major components: hard chain-of-thought, multi-task learning, and generation mask patterns. The experiment results demonstrate that DGRC significantly enhances generation performance, achieving a more than 2.5-fold improvement in BLEU scores.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19139
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DGRC: An Effective Fine-tuning Framework for Distractor Generation in Chinese Multi-choice Reading Comprehension
Lin, Runfeng
Xu, Dacheng
Wang, Huijiang
Chen, Zebiao
Wang, Yating
Liu, Shouqiang
Computation and Language
Artificial Intelligence
When evaluating a learner's knowledge proficiency, the multiple-choice question is an efficient and widely used format in standardized tests. Nevertheless, generating these questions, particularly plausible distractors (incorrect options), poses a considerable challenge. Generally, the distractor generation can be classified into cloze-style distractor generation (CDG) and natural questions distractor generation (NQDG). In contrast to the CDG, utilizing pre-trained language models (PLMs) for NQDG presents three primary challenges: (1) PLMs are typically trained to generate ``correct'' content, like answers, while rarely trained to generate ``plausible" content, like distractors; (2) PLMs often struggle to produce content that aligns well with specific knowledge and the style of exams; (3) NQDG necessitates the model to produce longer, context-sensitive, and question-relevant distractors. In this study, we introduce a fine-tuning framework named DGRC for NQDG in Chinese multi-choice reading comprehension from authentic examinations. DGRC comprises three major components: hard chain-of-thought, multi-task learning, and generation mask patterns. The experiment results demonstrate that DGRC significantly enhances generation performance, achieving a more than 2.5-fold improvement in BLEU scores.
title DGRC: An Effective Fine-tuning Framework for Distractor Generation in Chinese Multi-choice Reading Comprehension
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.19139